OBJECTIVES: To detect novel adverse events (AEs) of lurasidone by disproportionality analysis in FDA database of Adverse Event Reporting System (FAERS) using Data Mining Algorithms (DMAs).

METHODS: The FAERS database used in this study includes 37,57,794 Drug Event Combinations (DECs) which were reported from 2011 second quarter (Q2) to 2015 second quarter (Q2). Wherein, 533 DECs were associated with lurasidone. We considered a DEC for disproportionality analysis only if a minimum of ten reports are present in database for the given AEs. A total of 533 DEC was reported from 2011Q2 to 2015Q2 in USFDA AERS database. Out of 533 DECs, 198 were unique reactions. The most frequently used DMAs, namely, Reporting Odds Ratio (ROR), Proportional Reporting Ratio (PRR) and Information Component (IC) were applied retrospectively from 2011 (Q2) to 2015 (Q2) in FAERS Database. A value of ROR-1.96SE>1 and PRR≥2 were considered as the threshold for positive signal for completed suicide and a value of PRR≥2 were considered as the threshold for positive signal for hallucination.

RESULTS: The mean age of the patients of lurasidone associated events was found to be 44 years [95% CI: 36-51], nevertheless age was not mentioned in twenty-one reports. The reports by gender were evenly distributed with a male to female ratio of 1.25:1, though gender was not revealed in 38 reports. The data mining algorithms exhibited positive signal for “completed suicide” (ROR-1.96SE=1.01, PRR=4.69) and “hallucination” (PRR=2.81) upon analysis as those were well above the pre-set threshold.

CONCLUSIONS: Lurasidone associated two potential signals were generated by data mining in the FDA AERS database. The result requires an integration of further clinical surveillance for the quantification and validation of possible risks for the AEs reported of lurasidone.